Skip to main content
Glama
SMGilliatt

Knowledge Assistant MCP Server

by SMGilliatt

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RAG_TOP_KNoNumber of chunks to retrieve (default: 5)5
MODEL_NAMENoGemini model (default: gemini-2.0-flash)gemini-2.0-flash
OPIK_API_KEYNoOpik API key for observability – optional.
GOOGLE_API_KEYYesGoogle AI (Gemini) API key – required. Get from Google AI Studio.
EMBEDDING_MODELNoGoogle embedding model for RAG (default: models/gemini-embedding-001)models/gemini-embedding-001
CHROMA_COLLECTIONNoChromaDB collection name (default: knowledge_base)knowledge_base
OPIK_PROJECT_NAMENoOpik project name (default: knowledge-assistant)knowledge-assistant
CHROMA_PERSIST_DIRNoChromaDB persistence directory (default: ./chroma_data)./chroma_data

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SMGilliatt/knowledge-assistant-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server